• 대한조선학회논문집
• /
• 제56권6호
• /
• pp.473-479
• /
• 2019

Welding is one of the most popular joining methods and most welding quality estimation methods are executed using joined material. This paper propose welding quality estimation methods using dynamic current, voltage and resistance which are obtained during welding in real time. There are many kinds of welding method. Among them, we focused on the projection welding and gathered dynamic characteristics from two different types of projection welding. For image learning, graphs are drawn using obtained current, voltage and resistance, and the graphs are converted to images. The images are labeled with two sub-categories - normal and defect. For deep learning of images obtained from welding, Convolutional Neural Network (CNN) is applied, and Tensorflow was used as a framework for deep learning. With two resistance welding test datasets, we conclude that the Convolutional Neural Network helps in predicting the welding quality.

• 한국정밀공학회지
• /
• 제19권4호
• /
• pp.132-139
• /
• 2002

In GMAW(Gas Metal Arc Welding) processes, bead geometry (penetration, bead width and height) is a criterion to estimate welding quality. Bead geometry is affected by welding current, arc voltage and travel speed, shielding gas, CTWD (contact-tip to workpiece distance) and so on. In this paper, welding process variables were selected as welding current, arc voltage and travel speed. And bead geometry was reasoned from the chosen welding process variables using neuro-fuzzy algorithm. Neural networks was applied to design FL(fuzzy logic). The parameters of input membership functions and those of consequence functions in FL were tuned through the method of learning by backpropagation algorithm. Bead geometry could be reasoned from welding current, arc voltage, travel speed on FL using the results learned by neural networks. On the developed inference system of bead geometry using neuro-furzy algorithm, the inference error percent of bead width was within $\pm$4%, that of bead height was within $\pm$3%, and that of penetration was within $\pm$8%. Neural networks came into effect to find the parameters of input membership functions and those of consequence in FL. Therefore the inference system of welding quality expects to be developed through proposed algorithm.

• Journal of Welding and Joining
• /
• 제14권6호
• /
• pp.131-139
• /
• 1996

The response of the arc sensor using the welding current and/or welding voltage as its outputs has been obtained by the analysis and/or experiments of the static characteristics of arc sensor. But in order to improve the reliability of arc sensor, it is necessary to know its dynamic characteristics. So in this paper, it is presented the dynamic model of arc sensor including the power source, arc voltage, electrode burnoff rate, and wire feed rate. A numerical simulation of the dynamic model of arc sensor was implemented, computing the welding current with input of CTWD. The results of computer simulations and experiments of $CO_2$arc welding showed that a linear relationship between weaving center - weld line distance and current area difference was established. Additionally, a real-time weld seam tracking system interfaced with industrial welding robot was constructed, the result of the weld seam tracking experiment for weld line with an initial offset error of 5$^{\circ}$was good.

• 한국생산제조학회지
• /
• 제6권4호
• /
• pp.89-95
• /
• 1997

Welding technique is widely applied to general industry such as pressure vessel for chemical plant, pipe system, heavy industry, and automobile. There are some points which must be considered when robot system is used in welding automation process for productivity improvement. Welding quality is governed by heat input, and this quantity can be different according to shape, property, and thick of material . For desired heat input , weld input parameters such as welding voltage, current, and welding velocity must be determined with those consideration. Until now these parameters have been determined mainly by experience of operator. In this study, the size of welding zone was predicted by fuzzy rules were constructed from the relation between welding variables and weld pool size. Inverse model method which welding control input for welder is determined with optimum voltage and current by fuzzy controller is validatied by computer simulation.

• 전력전자학회:학술대회논문집
• /
• 전력전자학회 1999년도 전력전자학술대회 논문집
• /
• pp.585-590
• /
• 1999

The conventional $CO_2$ inverter arc machine has constant voltage output characteristic and uses constant wire speed controller for welding current control. By adoption of PWM inverter to the welding machine, the spattering was reduced rather than the thyrister arc welding machine or AC arc welding machine. Moreover, by the high switching frequency, the output reactor size could be reduced evidently. Recently, the studies on optimal voltage and current waveform for the welding performance improvement have been studied. In this paper, a new instantaneous output current control scheme during the short circuit mode was proposed and showed the capability of arc stability improvement and the reduction of spatter generation.

• Journal of Welding and Joining
• /
• 제19권3호
• /
• pp.252-254
• /
• 2001

• 한국기계가공학회지
• /
• 제16권1호
• /
• pp.112-117
• /
• 2017

The arc, generated by Tungsten Inert Gas(TIG) welding, is stable and provides excellent quality of the weld. Since automation is difficult, a lot of work is performed by hand. In addition, to obtain the uniform weld quality is difficult when using a base metal having a nonuniform welding line, or when welding inside a pipe. Generally, TIG welding power has the characteristic of constant-current. The welding voltage is changed in proportion to the arc length. Hence, the automatic voltage control equipment should be applied at the TIG welding system. The automatic voltage control equipment has been designed using LabVIEW software. It consists of a manufactured voltage divider circuit, and jig for moving the torch. The voltage measurements and driving of the motor were performed through the algorithm implementation in LabVIEW. Welding was conducted while increasing the arc length. In this process, it was confirmed that the automatic voltage control equipment kept the arc length constant.

• Journal of Welding and Joining
• /
• 제28권2호
• /
• pp.54-59
• /
• 2010

The effects of welding parameters such as contact tip-to-work distance (CTWD), voltage, and current on the weld metal diffusible hydrogen contents (HD) were investigated and rationalized by the calculation of heating time and amount of heat generated in the extension length of flux cored wire. As CTWD increased from 15 to 25mm, HD decreased from 8.46 to 5.45mL/100g deposited metal. Calculations showed that, with an increase of CTWD, the amount of heat generated increased from 46 to 92J in addition to an increase of heating time. Increase of current from 250 to 320A, however, gave little variation of HD. It showed that no significant change in the amount of heat generated was found, and heating time was decreased with an increase of current. It also showed that CTWD is more influential than voltage in relatively lower heat input ranges, while voltage is more in higher input ranges

• 한국산업융합학회 논문집
• /
• 제4권2호
• /
• pp.207-213
• /
• 2001

Welding variables and condition in gas metal arc welding (GMAW) effect on the weld quality and productivity, extensive research efforts have been made to analyze the welding variables and conditions. In this study dynamic behavior of GMAW system is investigated using the chararcteristic equations of the power supply. wire and welding arc. Characteristic equation of wire is modified to include the effect of droplets attached at the electrode tip. The dynamic characteristics of arc length, current, voltage with respect to the step, ramp inputs of CTWD was simulated. From results of simulation, some predictions about dynamic characteristics of GMAW and welding process are available. The proposed simulator and results appear to be utilized to determine the proper welding conditions, to be improved by considering power supply dynamic characteristics.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.166-166
• /
• 2000

This paper describes for applications of neural networks in the field of arc welding. Conventional, automated process generally involves sophisticated sensing and control techniques applied to various processing parameters. Welding parameters affecting quality include the arc voltage, the welding current and the torch travel speed. The relationship between the welding parameters and weld qualify is not a direct one, and in addition, the effect of the weld parameter variables are not independent of the each other - changing the welding current will affect the arc voltage, and so on. Finally, a suitable proposal to improve the construction of the model has also been presented in the paper.